Towards Knowledge-enriched Cross-Lingual Answer Validation

Our baseline approach from the 2012 year includes three language-independent methods for the task of answer validation. All methods are based on a scoring mechanism that reflects the degree of similarity between the question-answer pairs and the supporting text. We evaluate the proposed methods when using various string similarity metrics, such as exact matching, Levenshtein, Jaro and Jaro-Winkler. In addition to this baseline approach, we take advantage of the multilingual QA4MRE dataset, and devise an ensemble method, which chooses the answer indicated as correct by the largest number of analyses of the individual translations. Finally, we present a language-augmented method that enriches the questions and answers with paraphrases obtained by means of machine translation. We show that all of the described approaches achieve a significant improvement over the random baseline, and that both majority voting and language augmentation lead to superior accuracy as compared with the original method. However, the addition of some knowledge-based components in year 2013 plus the complexity of the datasets led to decrease in overall accuracy for Bulgarian language.